imback82 commented on code in PR #42577:
URL: https://github.com/apache/spark/pull/42577#discussion_r1385865564
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:
##########
@@ -170,6 +170,25 @@ case class CatalogTablePartition(
}
}
+/**
+ * A container for clustering information.
+ *
+ * @param columnNames the names of the columns used for clustering.
+ */
+case class ClusterBySpec(columnNames: Seq[UnresolvedAttribute]) {
+ override def toString: String = columnNames.map(_.name).mkString(",")
+}
+
+object ClusterBySpec {
+ def fromProperty(columns: String): ClusterBySpec = columns match {
+ case "" => ClusterBySpec(Seq.empty[UnresolvedAttribute])
+ case _ =>
ClusterBySpec(columns.split(",").map(_.trim).map(UnresolvedAttribute.quotedString))
Review Comment:
done
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/catalog/interface.scala:
##########
@@ -170,6 +170,25 @@ case class CatalogTablePartition(
}
}
+/**
+ * A container for clustering information.
+ *
+ * @param columnNames the names of the columns used for clustering.
+ */
+case class ClusterBySpec(columnNames: Seq[UnresolvedAttribute]) {
Review Comment:
I went with `Seq[NamedReference]` to be consistent with `*Transform`
(including `ClusterByTransform`). Also, some of the helper function
`FieldReference.unapply` returns `NamedReference`, so it's easier to work with
`NamedReference`.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/connector/expressions/expressions.scala:
##########
@@ -150,6 +153,41 @@ private[sql] object BucketTransform {
}
}
+/**
+ * This class represents a transform for [[ClusterBySpec]]. This is used to
bundle
+ * ClusterBySpec in CreateTable's partitioning transforms to pass it down to
analyzer.
+ */
+final case class ClusterByTransform(
+ columnNames: Seq[NamedReference]) extends RewritableTransform {
+
+ override val name: String = "cluster_by"
+
+ override def references: Array[NamedReference] = {
+ arguments.collect { case named: NamedReference => named }
Review Comment:
+1
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/command/v2/CreateTableClusterBySuite.scala:
##########
@@ -0,0 +1,61 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.command.v2
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.TableIdentifier
+import org.apache.spark.sql.connector.catalog.{Identifier,
InMemoryPartitionTable}
+import org.apache.spark.sql.connector.catalog.CatalogV2Implicits.CatalogHelper
+import org.apache.spark.sql.connector.expressions.{ClusterByTransform,
FieldReference}
+import org.apache.spark.sql.execution.command
+
+/**
+ * The class contains tests for the `CREATE TABLE ... CLUSTER BY` command to
check V2 table
+ * catalogs.
+ */
+class CreateTableClusterBySuite extends command.CreateTableClusterBySuiteBase
+ with CommandSuiteBase {
+ override def validateClusterBy(
+ tableIdent: TableIdentifier, clusteringColumns: Seq[String]): Unit = {
+ val catalogPlugin =
spark.sessionState.catalogManager.catalog(tableIdent.catalog.get)
+ val partTable = catalogPlugin.asTableCatalog
+ .loadTable(Identifier.of(Array(tableIdent.database.get),
tableIdent.table))
+ .asInstanceOf[InMemoryPartitionTable]
+ assert(partTable.partitioning ===
+ Array(ClusterByTransform(clusteringColumns.map(FieldReference(_)))))
+ }
+
+ test("test basic CREATE/REPLACE TABLE with clustering columns") {
+ withNamespaceAndTable("ns", "table") { tbl =>
+ spark.sql(s"CREATE TABLE $tbl (id INT) $defaultUsing CLUSTER BY (id)")
Review Comment:
this is testing replace table (let me clarify the test case name), which is
supported only with v2.
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala:
##########
@@ -297,6 +297,7 @@ case class PreprocessTableCreation(catalog: SessionCatalog)
extends Rule[Logical
val normalizedPartCols = normalizePartitionColumns(schema, table)
val normalizedBucketSpec = normalizeBucketSpec(schema, table)
+ val normalizedClusterBySpec = normalizeClusterBySpec(schema, table)
Review Comment:
done
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/command/CreateTableClusterBySuiteBase.scala:
##########
@@ -0,0 +1,66 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.command
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.catalyst.TableIdentifier
+
+/**
+ * This base suite contains unified tests for the `CREATE/REPLACE TABLE ...
CLUSTER BY` command
+ * that check V1 and V2 table catalogs. The tests that cannot run for all
supported catalogs are
+ * located in more specific test suites:
+ *
+ * - V2 table catalog tests:
`org.apache.spark.sql.execution.command.v2.CreateTableClusterBySuite`
+ * - V1 table catalog tests:
+ *
`org.apache.spark.sql.execution.command.v1.CreateTableClusterBySuiteBase`
+ * - V1 In-Memory catalog:
`org.apache.spark.sql.execution.command.v1.CreateTableClusterBySuite`
+ * - V1 Hive External catalog:
+ *
`org.apache.spark.sql.hive.execution.command.CreateTableClusterBySuite`
+ */
+trait CreateTableClusterBySuiteBase extends QueryTest with DDLCommandTestUtils
{
+ override val command = "CREATE/REPLACE TABLE CLUSTER BY"
+
+ protected val nestedColumnSchema: String =
+ "col1 INT, col2 STRUCT<col3 INT, `col4 1` INT>, col3 STRUCT<`col4.1` INT>"
+ protected val nestedClusteringColumns: Seq[String] =
+ Seq("col2.col3", "col2.`col4 1`", "col3.`col4.1`")
+
+ def validateClusterBy(tableIdent: TableIdentifier, clusteringColumns:
Seq[String]): Unit
Review Comment:
done
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2SessionCatalog.scala:
##########
@@ -19,13 +19,11 @@ package org.apache.spark.sql.execution.datasources.v2
import java.net.URI
import java.util
-
import scala.collection.mutable
import scala.jdk.CollectionConverters._
-
Review Comment:
done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
